Improved fruit-fly swarm algorithm for bathymetry survey by using autonomous surface vehicles /

Developing a powerful robotic system is not the only solution for solving complicated tasks. In fact, many simple swarm robots can be designed to cooperate and be able to achieve similar or even better result. It is undoubtedly more cost and time efficient to develop this simplistic swarming system....

Full description

Saved in:
Bibliographic Details
Main Author: Naing, Lwinthein (Author)
Format: Thesis
Language:English
Published: Kuala Lumpur : Kulliyyah of Engineering, International Islamic University Malaysia, 2018
Subjects:
Online Access:http://studentrepo.iium.edu.my/handle/123456789/4878
Tags: Add Tag
No Tags, Be the first to tag this record!
LEADER 034230000a22003010004500
008 181119s2018 my a f m 000 0 eng d
040 |a UIAM  |b eng  |e rda 
041 |a eng 
043 |a a-my--- 
050 0 0 |a TJ211.3 
100 1 |a Naing, Lwinthein,  |e author 
245 1 0 |a Improved fruit-fly swarm algorithm for bathymetry survey by using autonomous surface vehicles /  |c by Lwinthein Naing 
264 1 |a Kuala Lumpur :  |b Kulliyyah of Engineering, International Islamic University Malaysia,  |c 2018 
300 |a xiv, 144 leaves :  |b colour illustrations ;  |c 30cm. 
336 |2 rdacontent  |a text 
347 |2 rdaft  |a text file  |b PDF 
502 |a Thesis (MSMCT)--International Islamic University Malaysia, 2018. 
504 |a Includes bibliographical references (leaves 69-72). 
520 |a Developing a powerful robotic system is not the only solution for solving complicated tasks. In fact, many simple swarm robots can be designed to cooperate and be able to achieve similar or even better result. It is undoubtedly more cost and time efficient to develop this simplistic swarming system. The system can be applied in tasks such as exploration, surveillance, and tracking. In this paper, a swarm optimization algorithm is developed to be used in autonomous surface vehicle (ASV) system in order to locate specific location within the waterbody while performing bathymetry survey. The developed algorithm is based on the existing fruit-fly optimization algorithm (FOA) and Lévy fruit-fly optimization algorithm (LFOA). These existing algorithms have been developed to be used in practical environment. However, there are several limitations that the system cannot achieve. Thus, the newly proposed algorithm is developed to overcome these constraints in order to obtain better results. The proposed algorithm is called improved-LFOA, or IFOA. It was tested and benchmarked against other several optimization algorithms such as artificial bee colony, particle swarm optimization, covariance matrix adaptation evolution strategy (CMA-ES), FOA, and LFOA. In summary, IFOA's accuracy is comparable to CMA-ES which is one of the most powerful algorithms when it comes to high-dimensional optimization. Furthermore, it also performs exceptionally well in terms of convergence rate and accuracy of the results against FOA and LFOA. In another benchmarking against LFOA in 20 restricted virtual environmental conditions, IFOA shows better convergence rate on 19 different conditions. This suggest that IFOA is a suitable algorithm for being used in ASV system for exploration task during bathymetry survey. However, the proposed algorithm still has several limitations that still need to be improved further as it still fails to operate efficiently in certain terrains. 
596 |a 1 
655 7 |a Theses, IIUM local 
690 |a Dissertations, Academic  |x Department of Mechatronics Engineering  |z IIUM 
710 2 |a International Islamic University Malaysia.  |b Department of Mechatronics Engineering 
856 4 |u http://studentrepo.iium.edu.my/handle/123456789/4878 
900 |a sbh-aaz 
999 |c 440588  |d 472665 
952 |0 0  |6 T TJ 000211.3 N155I 2018  |7 0  |8 THESES  |9 762316  |a IIUM  |b IIUM  |c MULTIMEDIA  |g 0.00  |o t TJ 211.3 N155I 2018  |p 00010984163  |r 2019-12-12  |t 1  |v 0.00  |y THESIS 
952 |0 0  |6 TS CDF TJ 211.3 N155I 2018  |7 0  |8 THESES  |9 857794  |a IIUM  |b IIUM  |c MULTIMEDIA  |g 0.00  |o ts cdf TJ 211.3 N155I 2018  |p 00010984162  |r 1900-01-02  |t 1  |v 0.00  |y THESISDIG